Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "bigscience/bloom-1b7",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 2,
+  "seq_length": 4096,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fda8733b326cafe173f960229b4d8d5196bbcd567a0f1a6a5ef65efa6125484
+size 6889734991

runs/Dec07_07-34-33_4b26c24717a3/1670398487.7956586/events.out.tfevents.1670398487.4b26c24717a3.113.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94f72644454e2ad4bc2f6bc7744d3816e5552b6ae1b5f54a6b772e8b6a54123b
+size 5527

runs/Dec07_07-34-33_4b26c24717a3/events.out.tfevents.1670398487.4b26c24717a3.113.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da5821796b6c55f40a65dedd43179c6b7b61a0248884abec70889a1b7fada59
+size 4032

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5eb7575d5f91a715fc5139de1ca7c2f2749d3570d895b9972172407458ef36e
+size 3439